Bio
My specific research objectives involve bridging the gap between operations research and machine learning,
and finding novel applications in the various areas of economics.
From a methodology perspective, I conduct research in
Stochastic Optimization, in areas such as,
- Online Learning (Reinforcement Learning, Bandit Learning etc.)
- Sequential Decision Making (Monte Carlo Tree Search, Simulation etc.)
- Multi-Agent Competitive Games (Equilibrium Computation, Mechanism Design etc.)
From an application perspective I conduct research in
Applied Economics, in areas such as,
- Competitive Supply Chains (Inventory Control, Newsvendor Models)
- Revenue Management (Dynamic Pricing, Oligopoly Analysis)
My research goals contain a mix of theoretical analysis and empirical algorithmic results. Furthermore, I have experience in building production grade machine learning pipelines at scale for eCommerce and ad-tech companies.
Here is my
academic website at TU Munich.
Academic Background
- Technical University of Munich (2021-Present)
- PhD Candidate in Computer Science
- Advisor: Prof. Jalal Etesami
- Working Thesis: Robust Online Learning and Optimization in Applied Mult-Agent Systems
- University of Toronto (2015-2017)
- University of Toronto (2010–2015)
- BASc in Mechanical Engineering, with Honours
- Minor in Robotics & Mechatronics
Employment
- Zalando SE (2020-2021).
- Applied Scientist - AB Testing for Markets & Demand Planning
- Loblaw Digital (2018-2020).
- Data Scientist - Demand Forecasting & Customer Fulfilment
- StackAdapt (2016-2018).
- Data Scientist - Real Time Bidding Optimization & Fraud Detection
- Paytm Labs (2015-2016).
- Visiting Scientist - eCommerce Recommendation & Fraud Detection
Awards
- Mitacs Accelerate Industry Government Joint Research Grant (2015)
- Wallace G Chalmers Engineering Design Award (2013)
- Faculty of Applied Science Engineering Research Fellowship (2012)
- Cancer Care Ontario IDEA Challenge Development Grant (2012)
- Magna Family Scholarship (2010)